Viewing profile — jimfleming

From the tree docs: > tree has originally been part of TensorFlow and is available as tf.nest. The tf.nest docs can be found here and may be more useful for now: https://www.tensor…

I'm aware of that and I've done quite a bit of work on both spiking neural networks and modern deep learning. My point is that those complexities are not required to implement many…

> That needs to work before moving to more complexity. It really depends on what level of abstraction you care to simulate. OpenWorm is working at the physics and cellular level, f…

This functionality is built into OpenCV[0]. If you're using a reference image (or if you know the lens properties) it doesn't require ML. It's mostly just a matrix transform. [0] h…

I've noticed that many JAX libraries (including those from Google) seem to adopt an object-oriented style more similar to Torch/Keras rather than JAX's functional style demonstrate…

I think your conclusions are accurate. For many problems LightGBM or xgboost can often yield decent results in short amounts of time and for many problems that’s sufficient. A lot …

It’s really very problem dependent. I allude to a few low-hanging things in my post above: e.g. feature engineering. Just because neural networks have an easier time learning non-l…

It takes time and a lot of hands-on experience. Many ML teams tend to work on one or just a few tightly coupled project for years. By contrast, we’ve worked on a lot of unique proj…

More anecdata: we consistently outperform lightgbm, xgboost, random forests, linear models, etc. using neural networks even on smaller datasets. This applies whether we implemented…

> Seems indie frameworks in AI can't survive? AI frameworks are enormously complex pieces of software—a mixed bag of GPU acceleration, math utilities, low and high-level implementa…

The article's demonstration of a counting model is horribly inaccurate to the point where I'm not sure why it was included. Most people see "AI" as being either good at something o…

To those that are upvoting this and previous Swift + TF announcements: What are you excited about, specifically? Why Swift? Why not Julia? Is it the syntax? Types? Compilation? Per…

This is sort of true. Birds are significantly more energy efficient than planes for some kinds of flight. Birds are also able to perform maneuvers that planes cannot such as landin…

My point is that DQN is pretty far removed from the biological equivalent. It's impressive and useful but the main reason it succeeded was not because of some deep insight from neu…

Hyperparameter optimization (including architectures) is not really meta-learning. Meta-learning, also known as "learning to learn", is more like MAML[0], RL2[1], L2RL[2], etc. 0. …

> I believe his thinking was already proven, and going for emulating and integrating the known algorithms that the brain uses is the fastest way to reach AGI. That's a stretch cons…

> Has this been put into practice in any AI to date? Meta-learning is an active subfield of research in machine learning. Gödel machines may overlap with program synthesis as well …

Highway connections are actually used heavily in NLP in combination with LSTMs.

The paper[0] is less vague than the article. To put this in terms of reinforcement learning: 1. Sample actions from a random policy distribution. 2. Fit an inverse model with super…

A common misconception is that self-driving car companies (outside of a few smaller startups) are using RL to drive the car. They are not. They use deep learning for perception sys…

Numenta is probably the most direct / well-known example of what you're asking. They get mixed reactions from the community (some fair, some not). DeepMind occasionally publishes c…

Hopefully this leads to better temporal priors for machine learning models. Sequence encoding frequently uses position coding[0] but the typical approaches (e.g. low frequency sin …

In addition, multiple works[0][1] have discovered that grid cell representations arise from regularized recurrent networks when provided relative inputs to predict absolute outputs…

That's really cool and interesting. There may be a deeper meaning to what you saw but it would be a rather surprising result if there was conscious awareness of these structures si…